Computer Vision research from Iasonas Kokkinos demonstrates method neural networks can assist in the field, encompassing various methods into one system:

In this work we introduce a convolutional neural network (CNN) that jointly handles low-, mid-, and high-level vision tasks in a unified architecture that is trained end-to-end. Such a universal network can act like a ‘swiss knife’ for vision tasks; we call this architecture an UberNet to indicate its overarching nature.

We address two main technical challenges that emerge when broadening up the range of tasks handled by a single CNN: (i) training a deep architecture while relying on diverse training sets and (ii) training many (potentially unlimited) tasks with a limited memory budget. Properly addressing these two problems allows us to train accurate predictors for a host of tasks, without compromising accuracy. Through these advances we train in an end-to-end manner a CNN that simultaneously addresses (a) boundary detection (b) normal estimation © saliency estimation (d) semantic segmentation  (e) human part segmentation (f)  semantic boundary detection, (g) region proposal generation and object detection. We obtain competitive performance while jointly addressing all of these tasks in 0.7 seconds per frame on a single GPU.

You can view the academic paper here

Iasonas has also put together an online demo were you can upload an image to be processed and analyzed, which you can try out here

< Prev Next >